Skip to content
ADE Index

Agent vs Claude Code CLI vs Codex CLI vs Pi

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

This page compares the four CLI agents only. Claude Code has 4 other listings and Codex has 5 other listings, each with its own page.

How they differ

SystemsAgent 1 · Claude Code CLI 4 · Codex CLI 4 · Pi 4 · 1 in all
Nothing the others do not have
, ,
, ,
, ,
Show 1 shared
Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Checked for Claude Code CLI, Codex CLI and Pi, not yet for Agent: Price (Claude Code CLI: ; Codex CLI: ; Pi: ), Model providers (Claude Code CLI: , , , Microsoft Foundry (Azure AI Foundry), ; Codex CLI: , , , , LM Studio; Pi: , , , , , SpaceXSI (Grok), , , , , Z.ai, , , , , , , , , , OpenCode Console (OpenCode Zen), Microsoft Foundry (Azure AI Foundry), Meta AI (Llama), , , , , , , ), Bring your own key (Claude Code CLI: ; Codex CLI: ; Pi: )

Not yet checked for any of these tools: agents it runs.

Provider names use the same listing as each tool page. Dotted values open their quote.

What each can do

Select an answer to see the maker’s sentence, or what we searched.

We have not checked Agent’s capabilities yet. 30 capabilities are checked for at least two of these tools. 7 get different answers, among them Approval modes, Subagents, Plan mode and Undo file edits; 6 differ only in a limit. 7 others are checked for one tool only.

Differences only13
  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • No, per makerNothe maker says it does not
  • *its limit or add-on is named under the row
  • Emptynot yet checked

Models, keys and usage

Local modelsNot yet checked: Agent, Claude Code CLI
Not yet checked for Agent
Not yet checked for Claude Code CLI
Custom OpenAI-compatible endpointNot yet checked: Agent, Claude Code CLI
Not yet checked for Agent
Not yet checked for Claude Code CLI
Token and cost usageNot yet checked: Agent
Not yet checked for Agent
Token view for API users

MCP, hooks, skills and subagents

MCP serversNot yet checked: Agent
Not yet checked for Agent
local and remote
local and remote
local and remote
HooksNot yet checked: Agent
Not yet checked for Agent
SkillsNot yet checked: Agent
Not yet checked for Agent
SubagentsNot yet checked: Agent
Not yet checked for Agent
Not built in; Subagent example
PluginsNot yet checked: Agent
Not yet checked for Agent
Custom commandsNot yet checked: Agent
Not yet checked for Agent

Editors, scripts and CI

Editor integrationNot yet checked: Agent, Pi
Not yet checked for Agent
VS Code extension or JetBrains plugin
Codex editor extension
Not yet checked for Pi
Headless modeNot yet checked: Agent
Not yet checked for Agent
JSON outputNot yet checked: Agent
Not yet checked for Agent
GitHub integrationNot yet checked: Agent, Pi
Not yet checked for Agent
Claude Code GitHub Action
Codex GitHub Action
Not yet checked for Pi
Commit attribution controlNot yet checked: Agent, Codex CLI, Pi
Not yet checked for Agent
Not yet checked for Codex CLI
Not yet checked for Pi

Review, steer and undo

Plan modeNot yet checked: Agent
Not yet checked for Agent
Not built in; Plan Mode example
Read-only modeNot yet checked: Agent
Not yet checked for Agent
Through plan mode
Not built in; Plan Mode example
Review diffsNot yet checked: Agent, Pi
Not yet checked for Agent
Not yet checked for Pi
Undo file editsNot yet checked: Agent, Codex CLI
Not yet checked for Agent
Not yet checked for Codex CLI
Maker's git-checkpoint example

Parallel agents

Parallel sessionsNot yet checked: Agent, Codex CLI, Pi
Not yet checked for Agent
Not yet checked for Codex CLI
Not yet checked for Pi
Git worktreesNot yet checked: Agent, Pi
Not yet checked for Agent
Local execution only
Not yet checked for Pi

Context and memory

Project instruction filesNot yet checked: Agent
Not yet checked for Agent
Memory across sessionsNot yet checked: Agent, Pi
Not yet checked for Agent
Off by default; local memories
Not yet checked for Pi
Resume a sessionNot yet checked: Agent
Not yet checked for Agent
Browse past sessionsNot yet checked: Agent
Not yet checked for Agent

Remote and mobile control

Remote controlNot yet checked: Agent, Pi
Not yet checked for Agent
Needs a Claude plan, not an API key
To a running app server
Not yet checked for Pi
Steer from a phoneNot yet checked: Agent, Codex CLI, Pi
Not yet checked for Agent
Needs a Claude plan, not an API key
Not yet checked for Codex CLI
Not yet checked for Pi
NotificationsNot yet checked: Agent
Not yet checked for Agent
Depends on the terminal
Maker's notify example

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Agent
Not yet checked for Agent
Not on native Windows
Linux/WSL2 needs bubblewrap
Gondolin micro-VM example
Approval modesNot yet checked: Agent
Not yet checked for Agent
Runs in a containerNot yet checked: Agent, Claude Code CLI, Codex CLI
Not yet checked for Agent
Not yet checked for Claude Code CLI
Not yet checked for Codex CLI
The repo's Docker recipe
Telemetry opt-outNot yet checked: Agent, Codex CLI
Not yet checked for Agent
Not yet checked for Codex CLI

Images, web and your computer

Image inputNot yet checked: Agent
Not yet checked for Agent
Needs a compatible terminal
Fetch URLsNot yet checked: Agent, Codex CLI, Pi
Not yet checked for Agent
Not yet checked for Codex CLI
Not yet checked for Pi
Browser automationNot yet checked: Agent, Codex CLI, Pi
Not yet checked for Agent
Claude in Chrome extension
Not yet checked for Codex CLI
Not yet checked for Pi
Computer useNot yet checked: Agent, Codex CLI, Pi
Not yet checked for Agent
macOS only; Pro, Max or Ultra plan
Not yet checked for Codex CLI
Not yet checked for Pi
Voice inputNot yet checked: Agent, Pi
Not yet checked for Agent
Claude.ai sign-in; no cloud or SSH
Only in builds with voice
Not yet checked for Pi
Not yet checked: , , ,

Each answer is about the CLI agent in its column. Something the maker publishes separately, such as an editor plugin or a GitHub Action, shows as “With add-on”, even when it has its own listing here. How capabilities are checked

About these tools

Agent

Claude Code CLI

Codex CLI

Pi

How to read the Index score

At a glance

Index score out of 100

AgentNot enough data yetClaude Code CLI92Codex CLI91Pi78

Mindshare HN mentions, 90 days

Agent0Claude Code CLI4,602Codex CLI4,237Pi1,310

Adoption GitHub stars, not scored

Agent16Claude Code CLI156kCodex CLI136kPi123k

Release days last 90 days

Agent0Claude Code CLI57Codex CLI32Pi19

Lowest monthly plan billed monthly, lower is cheaper

AgentNot yet checkedClaude Code CLI$20/moCodex CLI$20/monthPiNot yet checked

Platforms systems and surfaces

Agent1Claude Code CLI5Codex CLI4Pi4

Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built

Differences only
4 of 4
AgentCLI agent
Claude Code CLIAnthropic · CLI agent
Codex CLIOpenAI · CLI agent
PiEarendil Works · CLI agent
Interface
Terminal session listing file searches and reads while tests run
Codex CLI explaining a codebase, with an updated plan checklist
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Local terminal coding agent with approvals and resumable sessions
Terminal coding tool that executes routine tasks and handles git workflows
Coding agent from OpenAI that runs locally on your computer
Minimal, extensible agent harness that you can make your own
Category
CLI agent
CLI agentClaude Code family
CLI agentCodex family
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Not yet checked
Plans
Not yet checked
Bring your own key
Not yet checked
Yes
Yes
Yes
Runs on
Linux
Not yet checked
Yes
Yes
Yes
Terminal
Yes
Yes
Yes
Yes
Web
Not yet checked
Yes
Not yet checked
Not yet checked
Windows
Not yet checked
Yes
Yes
Yes
macOS
Not yet checked
Yes
Yes
Yes
Models and agents
Model providers
Not yet checked
AnthropicGoogleAmazon BedrockMicrosoft Foundry (Azure AI Foundry)Claude apps gateway
OpenAIGoogleOllamaAmazon BedrockLM Studio
AnthropicOpenAIGoogleOpenRouterDeepSeekSpaceXSI (Grok)Amazon BedrockMoonshot AI
+22 more model providers
MistralGroqZ.aiMiniMaxVercel AI GatewayAzure OpenAIFireworksGitHub CopilotOpenCode GoTogether AIHugging FaceCerebrasOpenCode Console (OpenCode Zen)Microsoft Foundry (Azure AI Foundry)Meta AI (Llama)Cloudflare AI GatewayXiaomiCloudflare Workers AINVIDIABasetenQwenCloudRadius
and others; list may be partial
Models
Not yet checked
AnthropicAmazon BedrockMicrosoft FoundryGoogleClaude
OpenAIGPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
AnthropicOpenAIDeepSeekNVIDIA NIMGoogle GeminiMistralGroqCerebrasxAIOpenRouterVercel AI GatewayMiniMaxMoonshot AIQwenMetaHugging FaceFireworksTogether AIBaseten
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
0
57Most
32
19
Release days per week
Latest release, any channel
Not yet checked
v2.1.327 17 Nov 2026
v1.5.2 10 Nov 2026
Index score
Score and rank
Not enough data yet
92 #1 Score 91.6; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Mindshare
00 Hacker News mentions in the last 90 days
924,602 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
Adoption, not scored
2316 stars, read 18 Nov 2026
98156,056 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
96122,575 stars, read 18 Nov 2026
Votes
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
Rank history
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Agent vs Claude Code CLI vs Codex CLI vs Pi on YouTube

More comparisons

Build your own